{"id":"https://openalex.org/W4415190844","doi":"https://doi.org/10.1145/3731599.3767340","title":"Intelligent Sampling of Extreme-Scale Turbulence Datasets for Accurate and Efficient Spatiotemporal Model Training","display_name":"Intelligent Sampling of Extreme-Scale Turbulence Datasets for Accurate and Efficient Spatiotemporal Model Training","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4415190844","doi":"https://doi.org/10.1145/3731599.3767340"},"language":"en","primary_location":{"id":"doi:10.1145/3731599.3767340","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767340","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767340","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018102608","display_name":"Wesley Brewer","orcid":"https://orcid.org/0000-0002-3639-3956"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wesley Brewer","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101729172","display_name":"Muralikrishnan Gopalakrishnan Meena","orcid":"https://orcid.org/0000-0003-4048-4639"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Meena Gopalakrishnan","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029414305","display_name":"Matthias Maiterth","orcid":"https://orcid.org/0000-0001-8698-460X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthias Maiterth","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051291589","display_name":"Aditya Kashi","orcid":"https://orcid.org/0000-0003-2589-3792"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Kashi","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054451484","display_name":"Jong Youl Choi","orcid":"https://orcid.org/0000-0002-6459-6152"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jong Youl Choi","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013833305","display_name":"Pei Zhang","orcid":"https://orcid.org/0000-0002-8351-0529"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pei Zhang","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024349484","display_name":"Stephen Nichols","orcid":"https://orcid.org/0000-0003-3484-2735"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Nichols","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046961751","display_name":"Riccardo Balin","orcid":"https://orcid.org/0000-0002-1906-902X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Riccardo Balin","raw_affiliation_strings":["Argonne National Laboratory (ANL), Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory (ANL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006585024","display_name":"Miles M. P. Couchman","orcid":"https://orcid.org/0000-0002-4667-6829"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Miles Couchman","raw_affiliation_strings":["York University, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070074179","display_name":"Stephen de Bruyn Kops","orcid":"https://orcid.org/0000-0002-7727-8786"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen de Bruyn Kops","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005975375","display_name":"P. K. Yeung","orcid":"https://orcid.org/0000-0002-6278-6032"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P.K. Yeung","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119671325","display_name":"Daniel L. Dotson","orcid":"https://orcid.org/0009-0007-6209-809X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Dotson","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096909213","display_name":"Rohini Uma-Vaideswaran","orcid":"https://orcid.org/0000-0003-0583-6109"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohini Uma-Vaideswaran","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014538652","display_name":"Sarp Oral","orcid":"https://orcid.org/0000-0001-8745-7078"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarp Oral","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101916963","display_name":"Feiyi Wang","orcid":"https://orcid.org/0000-0002-0099-1559"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feiyi Wang","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5018102608"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":2.6085,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90582005,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9700999855995178,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9510999917984009,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6274999976158142},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6003000140190125},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5821999907493591},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5580000281333923},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5206999778747559},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45719999074935913},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4478999972343445},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4284000098705292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72079998254776},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6003000140190125},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5821999907493591},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5461999773979187},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5206999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5099999904632568},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.439300000667572},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26829999685287476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3731599.3767340","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767340","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.03872","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03872","pdf_url":"https://arxiv.org/pdf/2508.03872","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767340","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767340","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1],"end":[2],"of":[3,70,101],"Moore\u2019s":[4],"law":[5],"and":[6,52,60,93],"Dennard":[7],"scaling,":[8],"efficient":[9,40],"training":[10],"increasingly":[11],"requires":[12],"rethinking":[13],"data":[14,24],"volume.":[15],"Can":[16],"we":[17,31,78],"train":[18],"better":[19],"models":[20],"with":[21,58,98],"significantly":[22],"less":[23],"via":[25],"intelligent":[26,36],"subsampling?":[27],"To":[28],"explore":[29],"this,":[30],"develop":[32],"SICKLE,":[33],"a":[34,43,83],"sparse":[35],"curation":[37],"framework":[38],"for":[39],"learning,":[41],"featuring":[42],"novel":[44],"maximum":[45],"entropy":[46],"(MaxEnt)":[47],"sampling":[48,62],"approach,":[49],"scalable":[50],"training,":[51],"energy":[53,96],"benchmarking.":[54],"We":[55],"compare":[56],"MaxEnt":[57],"random":[59],"phase-space":[61],"on":[63,76],"large":[64],"direct":[65],"numerical":[66],"simulation":[67],"(DNS)":[68],"datasets":[69],"turbulence.":[71],"Evaluating":[72],"SICKLE":[73],"at":[74],"scale":[75],"Frontier,":[77],"show":[79],"that":[80],"subsampling":[81],"as":[82],"preprocessing":[84],"step":[85],"can,":[86],"in":[87],"many":[88],"cases,":[89],"improve":[90],"model":[91],"accuracy":[92],"substantially":[94],"lower":[95],"consumption,":[97],"observed":[99],"reductions":[100],"up":[102],"to":[103],"38\u00d7.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-15T00:00:00"}